Method and equipment for manufacturing micro-plastic Raman detection substrate

Abstract

The invention relates to the technical field of Raman detection substrate manufacturing, in particular to a micro-plastic Raman detection substrate manufacturing method and equipment, and the method comprises the following steps: preparing multiple groups of silver branch solutions by adopting different parameters; the multiple groups of silver branch solutions are subjected to modification pretreatment; modifying the multiple groups of silver branch solutions respectively; respectively taking out 1mL of the solution from the multiple groups of modified silver branch solutions, and dripping the solution onto common medium-speed qualitative filter paper to form a detection substrate; sEM and TEM characterization means are utilized to observe the morphology and structure of silver dendritic crystals in the silver dendritic solution prepared under different parameters; detecting the Raman signal enhancement effect of the detection substrate prepared under different parameters; respectively inputting parameters corresponding to the detection substrates with different numbers and Raman signal enhancement effects into a database; an optimization model is introduced, and the Raman enhancement effect is predicted; and according to the output of the optimization model, optimal parameters are selected, the silver branch solution is prepared by using the optimal parameters, and the equipment is used for storing, training and operating the optimization model.

Description

Technical Field

[0001] The invention relates to the technical field of Raman detection substrate manufacturing, and in particular to a method and equipment for manufacturing a microplastic Raman detection substrate. Background Art

[0002] The pollution of environmental water, drinking water and food by microplastics has attracted continuous attention. The accumulation of microplastics in the human body poses a health threat to the digestive system, circulatory system, etc. Studies have shown that it is related to diarrhea, cardiovascular and cerebrovascular diseases, and can induce immune system responses. At present, surface enhanced Raman scattering spectroscopy technology is one of the important detection methods for trace amounts of non-fluorescently labeled microplastics in the environment, but this method has high requirements for the preparation of the substrate and the Raman signal enhancement effect, and its actual detection application is limited due to the low concentration of actual samples. The existing patent with publication number CN114507849A discloses a surface enhanced Raman substrate and its preparation method that takes into account both stability and Raman intensity, using an electrodeposition method; the patent with publication number CN115445615A discloses a preparation method for a nanometal core-shell structure, using a constant current / constant voltage deposition method.

[0003] Existing Raman detection substrates for microplastics have problems such as complex preparation, difficult enrichment, and low detection sensitivity. Summary of the invention

[0004] The purpose of the present invention is to provide a method and equipment for preparing a microplastic Raman detection substrate, to prepare a detection substrate through a simple replacement reaction, and to predict the Raman enhancement effect based on an optimization model, to select optimized parameters (reaction time, reaction temperature, etc.), and to prepare a silver dendrite solution to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a method and device for preparing a microplastic Raman detection substrate, the method comprising the following steps:

[0006] Step S1, preparing multiple groups of silver dendrite solutions using different parameters; the different parameters include one or more of different temperatures, precursor concentrations and reaction times;

[0007] Step S2, performing pre-modification treatment on multiple groups of silver stick solutions respectively;

[0008] Step S3, modifying the multiple groups of silver branch solutions respectively;

[0009] Step S4, taking out 1 mL of solution from each of the modified multiple groups of silver stick solutions, and dropping the solution onto a common medium-speed qualitative filter paper to form a detection substrate; the upper portion of the medium-speed qualitative filter paper is provided with a number;

[0010] Step S5, using SEM and TEM characterization methods to observe the morphology and structure of silver dendrites in the silver dendrite solutions prepared under different parameters;

[0011] Step S6, using a microplastic sample solution with a particle size of 500 nm and a concentration of 0.1 g / L, to detect the Raman signal enhancement effect of the detection substrate prepared under different parameters;

[0012] Step S7, inputting the parameters and Raman signal enhancement effects corresponding to the detection substrates with different numbers into the database respectively;

[0013] Step S8, introducing an optimization model, and training the optimization model through a machine learning algorithm, so that the optimization model learns the relationship between the Raman signal enhancement effect and the parameters used in the preparation, thereby predicting the Raman enhancement effect;

[0014] Step S9: According to the output of the optimization model, the optimal parameters are selected, and the silver dendrite solution is prepared using the optimal parameters to improve the Raman detection effect of the detection substrate.

[0015] Preferably, the pre-treatment of the multiple groups of silver dendrite solutions comprises the following steps:

[0016] Add 10 μmol / L n-hexyl mercaptan solution to multiple groups of silver rod solutions and shake to mix;

[0017] React at room temperature for 2 hours;

[0018] After the reaction was completed, the mixture was washed three times with ultrapure water.

[0019] Preferably, the method of preparing multiple groups of silver dendrite solutions using different parameters comprises the following steps:

[0020] Remove the oxide layer on the surface of zinc sheet;

[0021] Silver nitrate solutions of different solubility are placed in a plurality of test tubes, each of the test tubes is marked with the same number as that on the medium-speed qualitative filter paper;

[0022] Immerse the zinc sheets into test tubes with different numbers;

[0023] Set different reaction time and temperature for each test tube;

[0024] Record the reaction time and temperature corresponding to each test tube.

[0025] Preferably, the modifying of the multiple groups of silver dendrite solutions respectively comprises the following steps:

[0026] Add 10 μmol / L n-hexylthiol solution to the silver rod solutions in the multiple test tubes obtained in step S2, and shake to mix;

[0027] React at room temperature for 2 hours;

[0028] After the reaction was completed, the mixture was washed three times with ultrapure water.

[0029] Preferably, the use of SEM and TEM characterization methods to observe the morphology and structure of silver dendrites in silver dendrite solutions prepared under different parameters comprises the following steps:

[0030] The surface morphology was observed by X-ray energy spectrometer to observe the purity of the silver dendrite substrate prepared with different parameters and give a purity score;

[0031] The penetration of electron beams is used to obtain the internal structural information of the silver dendrites, and the crystallinity of the silver dendrites is analyzed by selected area electron diffraction to give a structural score;

[0032] The purity score and structure score are calculated using a weighted average algorithm to form a quality score for the silver stick solution.

[0033] Preferably, the step of inputting the parameters and Raman signal enhancement effects corresponding to the detection substrates with different numbers into the database comprises the following steps:

[0034] Input the number, reaction time information, reaction temperature information and concentration information of the silver nitrate solution corresponding to each test tube into a database;

[0035] Inputting Raman signal enhancement effect information of detection substrates corresponding to different parameters into a database, wherein the Raman signal enhancement effect information includes a Raman detection characteristic spectrum;

[0036] The quality scores of the silver stick solutions were entered into a database.

[0037] Preferably, the introducing of the optimization model and training the optimization model by a machine learning algorithm comprises the following steps:

[0038] Obtain the number, reaction time information, reaction temperature information and concentration information of the silver nitrate solution from the database and establish a number-parameter feature vector

[0039]

[0040] The reaction time, reaction temperature, silver nitrate solution concentration, and quality score are normalized to form an input variable Q corresponding to a number i. i , multiple input variables Q i Construct an input variable set Q, where i = 1, 2, 3, ..., n; where n is the number of numbers;

[0041] Extracting the maximum signal intensity amplitude and the Raman shift corresponding to the maximum signal intensity amplitude from the Raman detection characteristic spectrum;

[0042] After normalizing the maximum signal strength amplitude, the output variable P corresponding to number i is formed. i , multiple output variables P i Construct an output variable set P, where i = 1, 2, 3, ..., n; where n is the number of multiple output variables;

[0043] Divide the output variable set and the input variable set into a training set and a test set;

[0044] Build an optimization model based on regression algorithm, in represents the predicted value of the optimization model corresponding to number i, x1, x2, x3, x4 represent input variables, x0 and Δx represent intercept and trimming variables respectively;

[0045] Train the optimization model through the training set and test the model performance through the test set;

[0046] Set the threshold M, when When , the optimization model is considered to be effective, where Y i , represent the actual value and the model predicted value respectively.

[0047] Preferably, the step of making the optimization model learn the relationship between the Raman signal enhancement effect and the parameters used in the preparation, thereby predicting the Raman enhancement effect, comprises the following steps:

[0048] The reaction time, reaction temperature, silver nitrate solution concentration, and quality score corresponding to different numbers are normalized and input into the optimization model as input variables, and the predicted maximum signal intensity amplitude is output;

[0049] Arrange the predicted values ​​of the optimization models corresponding to the multiple numbers in ascending order;

[0050] The reaction time, reaction temperature, and silver nitrate solution concentration information corresponding to the predicted value are obtained as the optimal parameters.

[0051] The present invention also provides a device, including a processor, a memory and a communication module, wherein the device is used to store, train and run an optimization model, wherein the processor is connected to the memory and the communication module respectively, and the processor is connected to a database via the communication module.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. The present invention prepares a silver dendrite substrate through a simple replacement reaction and performs mercaptoethanol modification to increase its enrichment effect on microplastics in the aqueous phase. With filter paper as the support, the silver dendrite substrate has a high filtration rate for microplastics in water samples and a good Raman signal enhancement effect, and can realize qualitative and quantitative detection of various microplastics such as PS, PE, PET, etc. with different particle sizes; the detection substrate is stored in the aqueous phase to prevent oxidation, achieve long-term stable storage, and has high practical application value.

[0054] 2. The present invention introduces an optimization model, trains the optimization model to learn the relationship between the Raman signal enhancement effect and the parameters used in the preparation, so as to predict the Raman enhancement effect; specifically: the reaction time, reaction temperature, silver nitrate solution concentration, and quality score corresponding to different numbers are normalized and input into the optimization model as input variables, and the predicted maximum signal intensity amplitude is output; the predicted values ​​of the optimization model corresponding to multiple numbers are arranged in ascending order; the number corresponding to the largest predicted value is obtained, and the solution preparation parameters (reaction time, reaction temperature, silver nitrate solution concentration information) are obtained according to the number-parameter feature vector, and this parameter is used as the optimization parameter, and the parameter is used to prepare the silver solution in the later preparation to improve the Raman signal enhancement effect of the detection substrate. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 is a flow chart of the method of the present invention;

[0056] Figure 2 This is an electron microscope scanning image of the modified detection substrate of the present invention;

[0057] Figure 3 The Raman detection result of 500nm polystyrene plastic by the detection substrate prepared by the present invention;

[0058] Figure 4 The characteristic spectra of Raman detection of different types of microplastics by the detection substrate modified with n-hexylthiol in the present invention;

[0059] Figure 5 Schematic diagram of the filtration and enrichment of microplastics by the detection substrate of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] See also Figure 1The present invention provides a technical solution: a method and device for preparing a microplastic Raman detection substrate, the method comprising the following steps:

[0062] Step S1, preparing multiple groups of silver dendrite solutions using different parameters; the parameters include one or more of temperature, precursor concentration and reaction time; in this embodiment, the precursor is a silver nitrate solution;

[0063] The specific process is as follows: remove the oxide layer on the surface of the zinc sheet by sanding with sandpaper or soaking in 0.02 mol / L dilute hydrochloric acid; place silver nitrate solutions of different solubility in multiple test tubes, each of which is marked with the same number as the medium-speed qualitative filter paper on the surface; immerse the zinc sheet in test tubes with different numbers; set a different reaction time and reaction temperature for each test tube; and record the reaction time and reaction temperature corresponding to each test tube.

[0064] Step S2, respectively subjecting multiple groups of silver branch solutions to pre-modification treatment; the specific steps are as follows:

[0065] Add 10 μmol / L n-hexyl mercaptan solution to multiple groups of silver dendrite solutions and shake to mix; react at room temperature for 2 hours; after the reaction, wash with ultrapure water for 3 times for later use.

[0066] Step S3, modifying the multiple groups of silver branch solutions respectively;

[0067] The specific steps are as follows: add 10 μmol / L n-hexyl mercaptan solution to the silver dendrite solutions in the multiple test tubes obtained in step S2, shake and mix; react at room temperature for 2 hours; after the reaction, wash with ultrapure water for 3 times for later use. Figure 2 As shown, the modified silver branches maintained their original morphology and were not damaged.

[0068] Step S4, taking out 1 mL of solution from each of the modified multiple groups of silver stick solutions, and dropping the solution onto a common medium-speed qualitative filter paper to form a detection substrate; the upper portion of the medium-speed qualitative filter paper is provided with a number;

[0069] Step S5: using SEM and TEM characterization methods to observe the morphology and structure of silver dendrites in the silver dendrite solutions prepared under different parameters, providing intuitive evidence for understanding how different parameters affect the properties of silver dendrites. The specific steps are as follows:

[0070] The surface morphology was observed by X-ray energy spectrometer to observe the purity of the silver dendrite substrate prepared with different parameters and give a purity score;

[0071] The penetration of electron beams is used to obtain the internal structural information of silver dendrites, and the crystallinity of silver dendrites is analyzed by selected area electron diffraction to give a structural score;

[0072] The purity score and structure score are calculated using a weighted average algorithm to form a quality score for the silver stick solution.

[0073] Step S6, using a microplastic sample solution with a particle size of 500 nm and a concentration of 0.1 g / L, to detect the Raman signal enhancement effect of the detection substrate prepared under different parameters; Figure 5 As shown, microplastics are mainly adsorbed on the modified silver branches and are not distributed on the exposed filter paper, indicating that the modified silver branch substrate has a better enrichment effect on microplastics; the filtration rate of the microplastic sample solution with a particle size of 500nm and a concentration of 0.1g / L is as high as over 95%.

[0074] Step S7, inputting the parameters and Raman signal enhancement effects corresponding to the detection substrates with different numbers into the database respectively;

[0075] In this embodiment, laser confocal Raman was used for detection, with the following parameters: 784 nm laser, 50x objective lens, laser power 20 mW, and integration time 10 s.

[0076] like Figure 3 Part A of Figure 2 compares the PS signal before and after enhancement, indicating that the prepared substrate has a good Raman signal enhancement effect on PS; Figure 3 In part B, as the concentration of microplastics increases, the Raman signal increases, allowing for more sensitive quantitative analysis.

[0077] like Figure 4 The prepared substrate can detect the characteristic peaks of various microplastics such as PE and PET, can realize qualitative analysis, and has universal applicability for rapid and sensitive detection of various microplastics.

[0078] Specifically, the number corresponding to each test tube, as well as the reaction time information, reaction temperature information and concentration information of the silver nitrate solution corresponding to the number are input into the database; the parameters are crucial to the formation of silver nanostructures, directly affecting their size, shape and distribution, and thus affecting the final Raman enhancement effect.

[0079] The Raman signal enhancement effect information of the detection substrate corresponding to different parameters is input into the database, wherein the Raman signal enhancement effect information includes the Raman detection characteristic spectrum; and the quality score of the silver branch solution is input into the database.

[0080] Step S8, introducing an optimization model, and training the optimization model through a machine learning algorithm, so that the optimization model learns the relationship between the Raman signal enhancement effect and the parameters used in the preparation, thereby predicting the Raman enhancement effect;

[0081] Step S9: According to the output of the optimization model, the optimal parameters are selected, and the silver dendrite solution is prepared using the optimal parameters to improve the Raman detection effect of the detection substrate.

[0082] The optimization model is introduced and trained by machine learning algorithm, including the following steps:

[0083] Obtain the number, reaction time information, reaction temperature information and concentration information of the silver nitrate solution from the database and establish a number-parameter feature vector

[0084]

[0085] The reaction time, reaction temperature, silver nitrate solution concentration, and quality score are normalized to form an input variable Q corresponding to a number i. i , multiple input variables Q i Construct an input variable set Q, where i = 1, 2, 3, ..., n; where n is the number of numbers;

[0086] Extracting the maximum signal intensity amplitude and the Raman shift corresponding to the maximum signal intensity amplitude from the Raman detection characteristic spectrum;

[0087] After normalizing the maximum signal strength amplitude, the output variable P corresponding to number i is formed. i , multiple output variables P i Construct an output variable set P, where i = 1, 2, 3, ..., n; where n is the number of numbers;

[0088] The output variable set and the input variable set are divided into a training set and a test set; the proportion of the training set is 80% and the proportion of the test set is 20%.

[0089] Build an optimization model based on regression algorithm, in represents the predicted value of the model corresponding to number i, x1, x2, x3, x4 represent input variables, x0 and Δx represent intercept and trimming variables respectively;

[0090] Train the optimization model through the training set and test the model performance through the test set;

[0091] Set the threshold M, when When , the optimization model is considered to be effective, where Y i , represent the actual value and the model predicted value respectively.

[0092] The trained optimization model can learn the relationship between the Raman signal enhancement effect and the parameters used in the preparation, so as to predict the Raman enhancement effect, which specifically includes the following steps:

[0093] The reaction time, reaction temperature, silver nitrate solution concentration, and quality score corresponding to different numbers are normalized and input into the optimization model as input variables, and the predicted maximum signal intensity amplitude is output;

[0094] Arrange the output values ​​of the optimization models corresponding to the multiple numbers in ascending order;

[0095] The number corresponding to the maximum signal intensity amplitude is obtained, and the corresponding reaction time, reaction temperature, and silver nitrate solution concentration information are obtained according to the number-parameter characteristic vector as the optimal parameters.

[0096] The present invention also provides a device, including a processor, a memory and a communication module, wherein the device is used to store, train and run an optimization model, wherein the processor is connected to the memory and the communication module respectively, and the processor is connected to a database via the communication module.

[0097] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0098] The scope of the present invention is defined by the attached claims and their equivalents. The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0099] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A method for preparing a microplastic Raman detection substrate, characterized in that: The method comprises the following steps: Step S1, preparing multiple groups of silver dendrite solutions using different parameters; the different parameters include one or more of different temperatures, precursor concentrations and reaction times; Step S2, performing pre-modification treatment on multiple groups of silver stick solutions respectively; Step S3, modifying the multiple groups of silver branch solutions respectively; Step S4, taking out 1 mL of solution from each of the modified multiple groups of silver stick solutions, and dropping the solution onto a common medium-speed qualitative filter paper to form a detection substrate; the upper portion of the medium-speed qualitative filter paper is provided with a number; Step S5, using SEM and TEM characterization methods to observe the morphology and structure of silver dendrites in the silver dendrite solutions prepared under different parameters; Step S6, using a microplastic sample solution with a particle size of 500 nm and a concentration of 0.1 g / L, to detect the Raman signal enhancement effect of the detection substrate prepared under different parameters; Step S7, inputting the parameters and Raman signal enhancement effects corresponding to the detection substrates with different numbers into the database respectively; Step S8, introducing an optimization model, and training the optimization model through a machine learning algorithm, so that the optimization model learns the relationship between the Raman signal enhancement effect and the parameters used in the preparation, thereby predicting the Raman enhancement effect; Step S9: According to the output of the optimization model, the optimal parameters are selected, and the silver dendrite solution is prepared using the optimal parameters to improve the Raman detection effect of the detection substrate.

2. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The pre-treatment of the plurality of groups of silver rod solutions respectively comprises the following steps: Add 10 μmol / L n-hexyl mercaptan solution to multiple groups of silver dendrite solutions and shake to mix; react at room temperature for 2 hours; After the reaction was completed, the mixture was washed three times with ultrapure water.

3. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The method of preparing multiple groups of silver dendrite solutions by using different parameters comprises the following steps: Remove the oxide layer on the surface of zinc sheet; Silver nitrate solutions of different solubility are placed in a plurality of test tubes, each of the test tubes is marked with the same number as that on the medium-speed qualitative filter paper; Immerse the zinc sheets into test tubes with different numbers; Set different reaction time and temperature for each test tube; Record the reaction time and temperature corresponding to each test tube.

4. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The method of modifying the plurality of groups of silver branch solutions respectively comprises the following steps: Add 10 μmol / L n-hexylthiol solution to the silver rod solutions in the multiple test tubes obtained in step S2, and shake to mix; React at room temperature for 2 hours; After the reaction was completed, the mixture was washed three times with ultrapure water.

5. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The method of using SEM and TEM characterization methods to observe the morphology and structure of silver dendrites in silver dendrite solutions prepared under different parameters includes the following steps: The surface morphology was observed by X-ray energy spectrometer to observe the purity of the silver dendrite substrate prepared with different parameters and give a purity score; The penetration of electron beams is used to obtain the internal structural information of the silver dendrites, and the crystallinity of the silver dendrites is analyzed by selected area electron diffraction to give a structural score; The purity score and structure score are calculated using a weighted average algorithm to form a quality score for the silver stick solution.

6. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The method of inputting the parameters and Raman signal enhancement effects corresponding to the detection substrates with different numbers into the database comprises the following steps: Input the number, reaction time information, reaction temperature information and concentration information of the silver nitrate solution corresponding to each test tube into a database; Inputting Raman signal enhancement effect information of detection substrates corresponding to different parameters into a database, wherein the Raman signal enhancement effect information includes a Raman detection characteristic spectrum; The quality scores of the silver stick solutions were entered into a database.

7. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The step of introducing the optimization model and training the optimization model through a machine learning algorithm includes the following steps: Obtain the number, reaction time information, reaction temperature information and concentration information of the silver nitrate solution from the database and establish a number-parameter feature vector The reaction time, reaction temperature, silver nitrate solution concentration, and quality score are normalized to form an input variable Q corresponding to a number i. i , multiple input variables Q i Construct an input variable set Q, where i = 1, 2, 3, ..., n; where n is the number of numbers; Extracting the maximum signal intensity amplitude and the Raman shift corresponding to the maximum signal intensity amplitude from the Raman detection characteristic spectrum; After normalizing the maximum signal strength amplitude, the output variable P corresponding to number i is formed. i , multiple output variables P i Construct an output variable set P, where i = 1, 2, 3, ..., n; where n is the number of multiple output variables; Divide the output variable set and the input variable set into a training set and a test set; Build an optimization model based on regression algorithm, in represents the predicted value of the optimization model corresponding to number i, x1, x2, x3, x4 represent input variables, x0 and Δx represent intercept and trimming variables respectively; Train the optimization model through the training set and test the model performance through the test set; Set the threshold M, when When , the optimization model is considered to be effective, where Y i , represent the actual value and the model predicted value respectively.

8. The method for preparing a microplastic Raman detection substrate according to claim 1, characterized in that: The method of making the optimization model learn the relationship between the Raman signal enhancement effect and the parameters used in the preparation, thereby predicting the Raman enhancement effect, comprises the following steps: The reaction time, reaction temperature, silver nitrate solution concentration, and quality score corresponding to different numbers are normalized and input into the optimization model as input variables, and the predicted maximum signal intensity amplitude is output; Arrange the output values ​​of the optimization models corresponding to the multiple numbers in ascending order; The reaction time, reaction temperature, and silver nitrate solution concentration information corresponding to the maximum signal intensity amplitude are obtained as the optimal parameters.

9. A device comprising a processor, a memory and a communication module, characterized in that: The device is used to store, train and run the optimization model described in claim 1, the processor is connected to the memory and the communication module respectively, and the processor is connected to the database through the communication module.

Images